Job Description

Key Responsibilities

• Design and build agentic LLM solutions (single- and multi-agent patterns) to solve real business problems across domains (e.g., customer support, document intelligence, knowledge retrieval).
• Build RAG pipelines end-to-end: data ingestion → chunking/embeddings → vector search → retrieval orchestration → response synthesis, with measurable quality.
• Implement prompt engineering and prompt orchestration (prompt chains, tool-calling, function calling), including prompt iteration and cost/latency optimisation.
• Develop production services/APIs for LLM applications (e.g., FastAPI/Flask/Streamlit) and integrate with enterprise systems and data sources.
• Apply guardrails to reduce hallucinations, enforce policy constraints, and ensure safe tool usage; implement evaluation strategies for LLM and RAG outputs.
• Collaborate with Data Engineering teams to ensure data quality, governance, and documentation standards, and with MLOps/Platform teams for CI/CD, monitoring, and reliable deployments.
• Create and maintain technical documentation, solution design artefacts, and reusable components for faster delivery and consistent engineering practices.

Must-Have Skills

5 to 12 years total experience, with hands-on LLM/GenAI delivery experience (preferably 1–3+ years building production-grade LLM apps).

LLM / GenAI & Agentic Engineering

• Hands-on experience with LLMs including Claude (Anthropic) and other leading models; strong understanding of capabilities, limitations, and use-case fit.
• Practical experience with RAG, embeddings, vector databases (e.g., FAISS/Pinecone/ChromaDB), semantic search, and retrieval quality evaluation.
• Experience with frameworks/tools such as LangChain, LangGraph, Hugging Face, or equivalent orchestration stacks.
• Experience building agentic workflows including tool calling/function calling; familiarity with “agentic architecture” concepts is valued.
• Exposure to Claude Code or similar coding-agent workflows is a plus (agentic coding that can work across codebases, run tests, and iterate).

Core Engineering

• Strong Python engineering skills (production-grade coding, testing, packaging, API development).
• Solid understanding of cloud platforms (Azure/AWS/GCP) and deployment basics (containers, CI/CD, monitoring).
• Strong communication skills—ability to translate business needs into technical solutions and articulate trade-offs clearly.

Mandatory Background (Non-negotiable)

• Prior experience in Data Engineering or Data Science
  • Data pipelines / ETL / ELT / orchestration, or
  • ML/NLP modelling lifecycle, experimentation, evaluation, or
  • Analytics engineering and data product delivery.

Good-to-Have / Preferred

• Fine-tuning approaches (e.g., LoRA/PEFT), prompt tuning, few-shot strategies, and model evaluation methods.
• Experience with enterprise-grade privacy/security considerations for GenAI solutions (data handling, redaction, access control).
• Experience with Azure stack components often used in GenAI (e.g., Azure AI Search / Azure OpenAI) is beneficial.

Education

Bachelor’s or Master’s degree in Computer Science, Data Engineering, Data Science, Information Systems, or related fields (or equivalent practical experience).

Key Responsibilities

• Design and build agentic LLM solutions (single- and multi-agent patterns) to solve real business problems across domains (e.g., customer support, document intelligence, knowledge retrieval).
• Build RAG pipelines end-to-end: data ingestion → chunking/embeddings → vector search → retrieval orchestration → response synthesis, with measurable quality.
• Implement prompt engineering and prompt orchestration (prompt chains, tool-calling, function calling), including prompt iteration and cost/latency optimisation.
• Develop production services/APIs for LLM applications (e.g., FastAPI/Flask/Streamlit) and integrate with enterprise systems and data sources.
• Apply guardrails to reduce hallucinations, enforce policy constraints, and ensure safe tool usage; implement evaluation strategies for LLM and RAG outputs.
• Collaborate with Data Engineering teams to ensure data quality, governance, and documentation standards, and with MLOps/Platform teams for CI/CD, monitoring, and reliable deployments.
• Create and maintain technical documentation, solution design artefacts, and reusable components for faster delivery and consistent engineering practices.

Must-Have Skills

5 to 12 years total experience, with hands-on LLM/GenAI delivery experience (preferably 1–3+ years building production-grade LLM apps).

LLM / GenAI & Agentic Engineering

• Hands-on experience with LLMs including Claude (Anthropic) and other leading models; strong understanding of capabilities, limitations, and use-case fit.
• Practical experience with RAG, embeddings, vector databases (e.g., FAISS/Pinecone/ChromaDB), semantic search, and retrieval quality evaluation.
• Experience with frameworks/tools such as LangChain, LangGraph, Hugging Face, or equivalent orchestration stacks.
• Experience building agentic workflows including tool calling/function calling; familiarity with “agentic architecture” concepts is valued.
• Exposure to Claude Code or similar coding-agent workflows is a plus (agentic coding that can work across codebases, run tests, and iterate).

Core Engineering

• Strong Python engineering skills (production-grade coding, testing, packaging, API development).
• Solid understanding of cloud platforms (Azure/AWS/GCP) and deployment basics (containers, CI/CD, monitoring).
• Strong communication skills—ability to translate business needs into technical solutions and articulate trade-offs clearly.

Mandatory Background (Non-negotiable)

• Prior experience in Data Engineering or Data Science
  • Data pipelines / ETL / ELT / orchestration, or
  • ML/NLP modelling lifecycle, experimentation, evaluation, or
  • Analytics engineering and data product delivery.

Good-to-Have / Preferred

• Fine-tuning approaches (e.g., LoRA/PEFT), prompt tuning, few-shot strategies, and model evaluation methods.
• Experience with enterprise-grade privacy/security considerations for GenAI solutions (data handling, redaction, access control).
• Experience with Azure stack components often used in GenAI (e.g., Azure AI Search / Azure OpenAI) is beneficial.

Education

Bachelor’s or Master’s degree in Computer Science, Data Engineering, Data Science, Information Systems, or related fields (or equivalent practical experience).

Key Responsibilities

• Design and build agentic LLM solutions (single- and multi-agent patterns) to solve real business problems across domains (e.g., customer support, document intelligence, knowledge retrieval).
• Build RAG pipelines end-to-end: data ingestion → chunking/embeddings → vector search → retrieval orchestration → response synthesis, with measurable quality.
• Implement prompt engineering and prompt orchestration (prompt chains, tool-calling, function calling), including prompt iteration and cost/latency optimisation.
• Develop production services/APIs for LLM applications (e.g., FastAPI/Flask/Streamlit) and integrate with enterprise systems and data sources.
• Apply guardrails to reduce hallucinations, enforce policy constraints, and ensure safe tool usage; implement evaluation strategies for LLM and RAG outputs.
• Collaborate with Data Engineering teams to ensure data quality, governance, and documentation standards, and with MLOps/Platform teams for CI/CD, monitoring, and reliable deployments.
• Create and maintain technical documentation, solution design artefacts, and reusable components for faster delivery and consistent engineering practices.

Must-Have Skills

5 to 12 years total experience, with hands-on LLM/GenAI delivery experience (preferably 1–3+ years building production-grade LLM apps).

LLM / GenAI & Agentic Engineering

• Hands-on experience with LLMs including Claude (Anthropic) and other leading models; strong understanding of capabilities, limitations, and use-case fit.
• Practical experience with RAG, embeddings, vector databases (e.g., FAISS/Pinecone/ChromaDB), semantic search, and retrieval quality evaluation.
• Experience with frameworks/tools such as LangChain, LangGraph, Hugging Face, or equivalent orchestration stacks.
• Experience building agentic workflows including tool calling/function calling; familiarity with “agentic architecture” concepts is valued.
• Exposure to Claude Code or similar coding-agent workflows is a plus (agentic coding that can work across codebases, run tests, and iterate).

Core Engineering

• Strong Python engineering skills (production-grade coding, testing, packaging, API development).
• Solid understanding of cloud platforms (Azure/AWS/GCP) and deployment basics (containers, CI/CD, monitoring).
• Strong communication skills—ability to translate business needs into technical solutions and articulate trade-offs clearly.

Mandatory Background (Non-negotiable)

• Prior experience in Data Engineering or Data Science
  • Data pipelines / ETL / ELT / orchestration, or
  • ML/NLP modelling lifecycle, experimentation, evaluation, or
  • Analytics engineering and data product delivery.

Good-to-Have / Preferred

• Fine-tuning approaches (e.g., LoRA/PEFT), prompt tuning, few-shot strategies, and model evaluation methods.
• Experience with enterprise-grade privacy/security considerations for GenAI solutions (data handling, redaction, access control).
• Experience with Azure stack components often used in GenAI (e.g., Azure AI Search / Azure OpenAI) is beneficial.

Education

Bachelor’s or Master’s degree in Computer Science, Data Engineering, Data Science, Information Systems, or related fields (or equivalent practical experience).

EXL (NASDAQ: EXLS) is a leading data analytics and digital operations and solutions company. We partner with clients using a data and AI-led approach to reinvent business models, drive better business outcomes and unlock growth with speed. EXL harnesses the power of data, analytics, AI, and deep industry knowledge to transform operations for the world’s leading corporations in industries including insurance, healthcare, banking and financial services, media and retail, among others. EXL was founded in 1999 with the core values of innovation, collaboration, excellence, integrity and respect. We are headquartered in New York and have more than 54,000 employees spanning six continents. For more information, visit www.exlservice.com EXL never requires or asks for fees/payments or credit card or bank details during any phase of the recruitment or hiring process and has not authorized any agencies or partners to collect any fee or payment from prospective candidates. EXL will only extend a job offer after a candidate has gone through a formal interview process with members of EXL’s Human Resources team, as well as our hiring managers.