Job Description

You might be our missing piece if you have:

• Strong Python skills and a solid software engineering foundation.

• Experience building production-grade backend applications with FastAPI, Flask, or Django.

• Hands-on experience designing, building, and deploying ML and/or GenAI solutions in production.

• Experience with GenAI frameworks such as LangChain, LangGraph, ADK, or Haystack.

• A good understanding of commercial LLM APIs and how to use them effectively in real products.

• Strong experience with RAG systems, including embeddings, vector search, retrieval pipelines, chunking, reranking, and context construction.

• Experience working with agentic systems, tool use, orchestration flows, and multi-step execution.

• Familiarity with MCP and its role in connecting agents with tools, data sources, and external systems.

• Experience implementing evaluation strategies for GenAI systems, including quality, latency, cost, and hallucination tracking.

• Comfort working with relational/non-relational databases, vector stores, and data pipelines for ML or GenAI use cases.

• Familiarity with Docker, containerized workflows, and MLOps practices such as CI/CD, experiment tracking, and model versioning.

• Experience building observable systems, with solid logging, monitoring, and debugging practices.

• Good judgment around privacy, security, and guardrails for AI systems.

• An interest in agentic coding and spec-driven development.

• Experience taking AI/ML work from exploration to production in a team setting.

• A collaborative mindset and willingness to support junior colleagues through reviews, pairing, and knowledge sharing.
  
  

We would be thrilled if you have:

• Experience evaluating and improving agentic systems in real-world settings.

• Hands-on experience with MCP-based integrations.

• Familiarity with prompt engineering and context engineering.

• Exposure to research and the ability to turn ideas into practical solutions.

• Comfort with cloud infrastructure such as AWS, Azure, GCP, or DigitalOcean.

• Hands-on experience with Databricks or Apache Spark.

• Experience with tooling for LLM observability or evaluation.

• Familiarity with authentication, authorization, and data governance in enterprise environments.

• Experience contributing to technical communities, talks, or internal documentation.

We will be working together on the following:

• Understanding client needs and helping shape practical AI solutions.

• Designing and delivering agentic RAG systems that are reliable and production-ready.

• Building integrations between agents, tools, and external systems, including through MCP where relevant.

• Owning AI/ML components from prototyping through deployment, monitoring, and iteration.

• Applying evaluation approaches for retrieval, generation, and agent behavior.

• Contributing to good engineering practices around reproducibility, observability, scalability, and reliability.

• Working closely with product, platform, and infrastructure teams.

• Troubleshooting production issues and improving system reliability over time.

• Supporting the team through code reviews, pair programming, and shared learning.

• Staying close to industry developments and applying what is useful in practice.