Overview
Hands-on AI Engineer role to design, build, and deploy production-grade AI-driven systems within enterprise environments, delivering real-world AI/ML solutions that address actual customer needs.
What you'll do
- Design and implement AI agents, including RAG pipelines, orchestration workflows, and tool invocation
- Build evaluation frameworks to measure system accuracy, latency, cost, and reliability
- Implement observability and monitoring across the AI system lifecycle
- Integrate with multiple AI providers and develop abstraction layers for multi-model architectures
- Optimize AI systems for performance, cost, and scalability
- Build and deploy AI-powered applications tightly coupled with real business workflows
- Integrate AI systems into existing enterprise platforms and APIs
- Debug and optimize live production systems
- Collaborate closely with both client and internal engineering teams
- Participate in technical design discussions with a focus on implementation
What you'll need
- 4+ years of experience building and deploying AI/ML systems in production (beyond demos or experimentation)
- Track record of architecting, building, and successfully shipping AI/ML or software solutions using modern AI-assisted workflows
- Strong understanding of AI system evaluation and measurement, including offline metrics, online monitoring, LLM-as-judge processes, regression testing, and cost/latency tracking
- Practical judgment in retrieval and agent design trade-offs, with the ability to explain and choose between RAG, agent loops, and workflows as needed
- Hands-on experience with LLM platforms (OpenAI, Anthropic, Google Vertex, or similar) and orchestration/harness patterns
- Proficiency in Python
- Solid backend engineering skills: building and deploying APIs, working with Docker, and navigating cloud-native environments (containers, basic infrastructure)
- Strong software engineering fundamentals: writing maintainable, production-grade code
- Experience with CI/CD pipelines, infrastructure as code, and production observability
- Ability to debug and optimise systems already in production
- Strong communication skills, including the ability to explain technical trade-offs to non-technical stakeholders
Nice to have
- Familiarity with prompt optimization or evaluation tools (DSPy, MLflow, promptfoo, RAGAS, etc.)
- LLMOps/MLOps experience: building robust, monitored, self-healing AI systems
- Experience with harness engineering (e.g., developing on/with Goose, Pi, Claude Code, Codex)
- Databricks experience
- Experience with cloud platforms such as AWS, Azure, or GCP
- Experience with FastAPI, Pydantic, PostgreSQL, MySQL, or DuckDB
- Experience using the Claude SDK or OpenAI SDK
- Additional programming languages beyond Python, such as TypeScript or Go
- Experience mentoring or upskilling fellow engineers
Details
- Location: Pune
- This is a 100% hands-on engineering role
Read the full description and apply on the company’s own careers page.