Your role
As an AI Engineer, the selected candidate will build and ship AI-powered tools alongside a small, technically focused team. This is a hands-on engineering role: the candidate will write Python, work with LLMs and agent frameworks, integrate APIs, and help deploy systems that real business teams depend on. Guidance will be provided by senior engineers and the AI Engineering Manager, and the successful candidate is expected to grow quickly — both in AI engineering depth and in the ability to take on problems with increasing independence over time. This role is based in India and reports to the AI Engineering Manager. The candidate must be available for overlap with the core team during morning IST hours to support collaboration and code reviews across time zones.
What you’ll do
- Design, build, and maintain production-grade AI systems, including multi-agent workflows, RAG applications, workflow automation, and LLM-powered services.
- Lead the technical implementation of complex AI initiatives from discovery through deployment.
- Architect scalable backend services, APIs, evaluation pipelines, and retrieval systems.
- Improve reliability, observability, and performance of production AI applications.
- Define engineering standards, reusable components, and best practices for AI development.
- Collaborate directly with business stakeholders to understand problems and translate them into scalable AI solutions.
- Evaluate new foundation models, frameworks, and prompting strategies and make recommendations for adoption.
- Build evaluation frameworks and automated testing strategies for LLM-based systems.
- Mentor junior engineers through code reviews, technical guidance, and design discussions.
- Participate in architectural planning, sprint planning, technical reviews, and cross-functional initiatives.
- Drive continuous improvements in engineering processes, documentation, and operational excellence.
Skills you’ll bring
- 5+ years of experience in software engineering, machine learning engineering, AI engineering, or a similar technical role.
- Strong Python development skills with experience building and maintaining production systems.
- Deep understanding of LLMs, prompting techniques, structured outputs, tool calling, function calling, and AI application architectures.
- Experience designing and deploying RAG systems, including chunking strategies, embeddings, retrieval optimization, reranking, and evaluation.
- Experience building agentic workflows using frameworks such as LangGraph, LangChain,, OpenAI Agents SDK, or similar.
- Experience integrating external APIs and enterprise systems.
- Strong understanding of software engineering best practices, including testing, CI/CD, observability, monitoring, and production deployments.
- Experience working with cloud platforms (preferably GCP) and containerized applications.
- Strong debugging and problem-solving skills.
- Excellent written and verbal English communication.
- Ability to independently manage projects and influence technical decisions across teams.
