19 hours ago
Bengaluru, IndiaSenior
Responsibilities
- Design and build production-grade agentic systems with multi-agent orchestration, RAG pipelines, policy-based routing, tool invocation, memory management, and observability.
- Own RAG pipelines, including embeddings, chunking strategies, vector search, context-window engineering, and quality tuning.
- Integrate OpenAI, Anthropic, Vertex AI, and open-source models with provider abstraction, fallback routing, and token, cost, and latency management.
- Implement production LLMOps, including evaluation harnesses, prompt versioning, observability, cost monitoring, and safety monitoring.
- Embed with client engineering teams to lead technical design sessions, workshops, proofs of concept, code-with sessions, and architecture walkthroughs.
- Create reusable engineering patterns, accelerators, and playbooks for future client engagements.
- Define and analyze metrics for agent accuracy, latency, safety, and cost-effectiveness and present recommendations to stakeholders.
Requirements
- 7.5–10 years of software engineering experience in production environments.
- At least one year of hands-on experience designing and deploying agentic AI solutions in production.
- Production-depth experience with LangGraph, CrewAI, AutoGen, or an equivalent agentic orchestration framework.
- Production experience calling OpenAI, Anthropic, or Vertex AI APIs, including provider abstraction, token management, and latency and cost tradeoffs.
- Ownership of RAG pipelines involving embeddings, chunking strategies, vector databases, and context engineering.
- Experience with LLMOps fundamentals, including evaluation harness design, prompt versioning, and production observability.
- Cloud-native engineering experience with Kubernetes, Docker, microservices, serverless systems, and infrastructure as code using Terraform or Helm.
- Strong Python, Java, or equivalent backend-language experience, including production debugging and observability.
- Candidates with multiple shipped production agentic systems are preferred over candidates with only passive AI exposure.
- 15 years of full-time education.
Benefits
- The role offers breadth across industries and enterprise technology stacks, vendor fellowship access inside Anthropic, OpenAI, Microsoft, and Google engineering teams, and a pathway to the Forward Deployed Engineer programme.
Tech Stack
Categories
About Accenture
Accenture is a global professional services firm providing management consulting, systems integration and technology, cybersecurity, and business process outsourcing for enterprises and governments. It operates a services-driven model delivering projects and managed services, often with major cloud and software partners, across industries worldwide. Headquartered in Dublin and publicly traded on the NYSE (ACN), it originated as Andersen Consulting and adopted the Accenture name in 2001.