14 days ago
Pune, India or Bengaluru, IndiaStaff+
Responsibilities
- Own AI/ML and Generative AI solutions end to end, including data pipelines, model and prompt workflows, APIs, evaluation, deployment, observability, and continuous optimization.
- Design enterprise RAG platforms with secure ingestion, chunking, embeddings, hybrid and vector search, reranking, citations, and access-aware retrieval.
- Build production agentic systems with tool and function calling, structured outputs, planning, memory, multi-agent orchestration, human-in-the-loop approvals, failure recovery, and auditable traces.
- Architect and operate MCP clients and servers with secure transports, authentication, least-privilege access, tenant isolation, and protections against prompt injection and unsafe tool execution.
- Integrate agents with document repositories, source control, ticketing systems, databases, ERP/CRM systems, and cloud services through reusable connectors and governance patterns.
- Define evaluation strategies and quality gates for accuracy, groundedness, safety, latency, and cost, and establish observability for agent and MCP activity.
- Build production Python services and deploy them on AWS or Azure using Docker, Kubernetes, and infrastructure as code.
- Lead design and architecture reviews, partner with product, architecture, data science, security, and business stakeholders, and mentor engineers.
Requirements
- Bachelor's or Master's degree in Computer Science, Data Science, AI/ML, Engineering, or a related field, or equivalent practical experience.
- 5–9 years of experience developing production software, data, ML, or AI solutions, including hands-on delivery of GenAI/LLM applications.
- Advanced Python skills and practical experience with data and ML libraries such as pandas, NumPy, scikit-learn, PyTorch, or TensorFlow.
- Strong knowledge of LLM and agentic architecture, including prompting, context engineering, embeddings, RAG, tool and function calling, structured outputs, orchestration, evaluation, and human-in-the-loop controls.
- Experience designing APIs, distributed services, and event-driven or asynchronous workflows with secure tool execution for AI agents.
- Hands-on Git and GitHub experience with CI/CD workflows for automated builds, testing, security scanning, and deployment.
- Strong AWS or Azure experience with Docker-based containerized deployment, plus expected Kubernetes and infrastructure-as-code experience.
- A current, role-relevant AWS AI/ML certification or Microsoft Azure AI certification is mandatory.
- Production Model Context Protocol experience is mandatory, including consuming and developing MCP servers, integrating clients with agent frameworks, defining tools/resources/prompts, managing transports, and implementing security, approvals, testing, and tracing.
- Experience with MLOps/LLMOps practices such as experiment tracking, model and prompt versioning, tracing, evaluation, monitoring, and cost optimization.
- Preferred experience includes GenAI and agent frameworks, enterprise search and vector technologies, LLMOps and observability platforms, SQL and data modeling, streaming, workflow orchestration, data lakes or lakehouses, responsible AI, model risk management, data governance, privacy, regulatory compliance, mentoring, and reusable platform or open-source work.
Benefits
- Full-time roles include medical, dental, and vision insurance, a 401(k) with company match, and paid time off.
- The company describes a flexible, inclusive environment with progressive benefits, mentorship, and well-being support.
Tech Stack
Categories
