Job Description

We are looking for a Software Engineer to work on optimization algorithms and applied ML for
AI-assisted engineering automation. This role is ideal for someone who enjoys planning problems,
constraint handling, benchmarking, evaluation metrics, and practical ML experiments that improve
engineering quality and efficiency over time.

WHAT YOU WILL DO:
- Develop optimization and planning algorithms for complex engineering workflows.
- Build constraint-handling logic for quality, efficiency, manufacturability-related decisions, and
engineering review.
- Create benchmarking and visual/debug tools to compare algorithm behavior across representative
cases.
- Define and track metrics for automation quality, runtime, constraint violations, rework reduction, and engineering acceptance.
- Explore applied ML approaches for prediction, candidate ranking, learned cost functions, and future optimization use cases.
- Collaborate with platform, AI, and domain engineers to turn algorithmic ideas into maintainable
software.

REQUIRED SKILLS:
- Strong Python programming skills.
- Good fundamentals in data structures and algorithms.
- Exposure to graph algorithms, pathfinding, optimization, computational geometry, numerical methods, or applied ML.
- Ability to reason about constraints, edge cases, tradeoffs, and performance.
- Curiosity to learn semiconductor test and validation workflows deeply.
- Comfortable using AI tools for coding, debugging, experimentation, and learning.
- Strong M.Tech/MS graduates with 2-4 years of experience may also be considered if they have
relevant projects or research in applied ML, optimization, algorithms, robotics/path planning,
operations research, reinforcement learning, or computational geometry.

Qualifications

Experience: 2-4 years

GOOD TO HAVE:
- C++, Rust, NumPy, SciPy, NetworkX, OR-Tools, PyTorch, TensorFlow, JAX, or similar tools.
- Robotics planning, GIS/map routing, CAD/CAM, game pathfinding, operations research, scheduling, or competitive programming experience.
- Hands-on reinforcement learning, combinatorial optimization, or learned heuristic experience.
- Experience building experiments, benchmarks, evaluation harnesses, or visualization tools.
- Exposure to semiconductor, ATE, hardware validation, manufacturing automation, or engineering
automation domains.