9 days ago
Bengaluru, IndiaSenior
Responsibilities
- Architect complex AI systems involving multi-agent orchestration, large-scale RAG pipelines, and production LLM infrastructure.
- Own end-to-end delivery of AI features from conception through implementation, rollout, and production.
- Establish patterns, frameworks, and best practices for AI platform components across the engineering organization.
- Build high-scale data pipelines processing millions of records and manage embeddings for cost and latency optimization.
- Mentor SDE-II and junior engineers through code reviews, design discussions, and pairing sessions.
- Design AI evaluation frameworks, implement guardrails, and lead AI quality and safety initiatives.
- Collaborate with Product, Data Science/Engineering, and Platform teams on roadmap and technical strategy.
- Optimize production systems for performance, cost, and reliability, and troubleshoot complex production issues.
Requirements
- 5+ years of software engineering experience, including 2+ years building production LLM or GenAI systems at scale.
- Expert Python skills, including asynchronous programming, performance optimization, and production-grade testing.
- Deep hands-on experience with ML/LLM frameworks such as PyTorch, Hugging Face, LangChain, LlamaIndex, or Ray.
- Experience building and scaling vector search systems using Elasticsearch, Pinecone, Weaviate, or FAISS.
- Strong system design skills involving microservices, distributed systems, and event-driven architectures such as Kafka, SQS, or Kinesis.
- Production experience with Kubernetes, Docker, and cloud infrastructure, preferably AWS.
- Expertise in prompt engineering, prompt fine-tuning, embeddings, RAG, token management, and inference optimization.
- Technical leadership experience driving architecture decisions, mentoring engineers, and shipping complex projects.
- Strong communication and cross-functional collaboration skills.
- Preferred experience includes high-throughput inference with Ray, Triton, vLLM, or TensorRT; LLM evaluation with RAGAS or custom harnesses; multi-agent systems; AI cost optimization; open-source AI contributions or published research; and high-growth startup or 0-to-1 AI product experience.
Benefits
- Hybrid position requiring onsite work in the Bengaluru, India office as needed; candidates must be based in India.
- Inclusive and supportive workplace focused on culture add and equal employment opportunity.
Tech Stack
Categories
