Agentic AI Developer - AI and Data Science Engineer III

ConvergeCONSUMER™ is a product-driven business that combines differentiated consumer insights with robust prediction and optimization capabilities to help consumer-focused businesses improve decision-making and deliver personalized experiences to drive growth, consumer loyalty, and profitability. We operate with the speed and agility of a startup within the world’s largest professional services firm.

Our purpose

Deloitte’s purpose is to make an impact that matters for our people, clients, and communities. At Deloitte, purpose is synonymous with how we work every day. It defines who we are. Our purpose comes through in our work with clients that enables impact and value in their organizations, as well as through our own investments, commitments, and actions across areas that help drive positive outcomes for our communities. Our people and culture

Our inclusive culture empowers our people to be who they are, contribute their unique perspectives, and make a difference individually and collectively. It enables us to leverage different ways of thinking, ideas and perspectives, and bring more creativity and innovation to help solve our clients’ most complex challenges. This makes Deloitte one of the most rewarding places to work. Professional development

At Deloitte, professionals have the opportunity to work with some of the best and discover what works best for them. Here, we prioritize professional growth, offering diverse learning and networking opportunities to help accelerate careers and enhance leadership skills. Our state-of-the-art DU: The Leadership Center in India, located in Hyderabad, represents a tangible symbol of our commitment to the holistic growth and development of our people. Explore DU: The Leadership Center in India. Benefits to help you thrive

At Deloitte, we know that great people make a great organization. Our comprehensive rewards program helps us deliver a distinctly Deloitte experience that helps that empowers our professionals to thrive mentally, physically, and financially—and live their purpose. To support our professionals and their loved ones, we offer a broad range of benefits. Eligibility requirements may be based on role, tenure, type of employment and/ or other criteria. Learn more about what working at Deloitte can mean for you.

Recruiting tips

From developing a stand out resume to putting your best foot forward in the interview, we want you to feel prepared and confident as you explore opportunities at Deloitte. Check out recruiting tips from Deloitte recruiters.

Requisition code: 374375

Required

• 2–3+ years of hands-on AI engineering experience, including deploying LLM-based applications to production.
• Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.

Must have engineering

• Python, FastAPI, and REST APIs.
• PostgreSQL.
• Docker, Kubernetes (GKE), and GCP, including Vertex AI.
• CI/CD and system design for scalable AI applications.

Education

BE/B.Tech/MS/M.Tech degree or equivalent from accredited university

Bachelor’s degree in Computer Science, Information Systems, or another relevant discipline, or equivalent experience.

• A2A protocol and other agent frameworks (e.g., OpenAI Agents SDK, CrewAI, Google ADK).
• Agent security and guardrails, including prompt-injection defense.
• Cost and latency optimization (caching, model routing).
• Redis, Kafka/Pub/Sub, Celery, and Elasticsearch.
• Terraform, Helm, and OpenTelemetry.
• Fine-tuning or working with open-source LLMs.

• Build and ship production AI agents, from single-agent tool use to multi-agent workflows, using LangGraph, LangChain, or similar frameworks.
• Apply the right agent pattern to the problem — ReAct, plan-and-execute, reflection, deep agents, and human-in-the-loop (HITL).
• Design and deliver RAG pipelines: embeddings, vector databases, hybrid search, and reranking.
• Build SQL and dataframe agents that let users interrogate consumer data in natural language.
• Integrate tools and external systems through MCP (Model Context Protocol), tool calling, and structured outputs.
• Manage agent context and memory so agents stay context-aware across steps and sessions, within context window limits.
• Define and run evaluation and observability for LLM features — LLM-as-a-judge, LangSmith and/or Langfuse — and act on what the results show.
• Build and maintain the FastAPI services, data access, and deployment pipelines that carry these capabilities into production.
• Work across multiple LLM providers (OpenAI, Anthropic, Gemini) and own prompt quality, cost, and latency.

• Collaborate with product, data science, and engineering peers to turn consumer problems into shipped AI features.

• Experience building and shipping AI agents, from single-agent tool use to multi-agent workflows, using LangGraph, LangChain, or similar frameworks.
• Familiarity with agent patterns such as ReAct, plan-and-execute, reflection, deep agents, and human-in-the-loop (HITL).
• Understanding of reasoning concepts and how to implement them, such as explicit reasoning layers (e.g., sequential thinking) versus a model’s native reasoning.
• Experience delivering SQL and/or dataframe agents to production.
• MCP (Model Context Protocol), tool calling, and structured outputs.
• Context management and memory: keeping agents context-aware across steps and sessions, within context window limits.
• RAG: embeddings, vector databases, hybrid search, and reranking.
• Evaluation and observability: LLM-as-a-judge, LangSmith and/or Langfuse.
• Experience with multiple LLM providers (OpenAI, Anthropic, Gemini) and strong prompt engineering skills.

Bengaluru/Hyderabad/Pune/Chennai/Mumbai/Gurgaon/Kolkata

11 AM to 8 PM or 2 PM to 11 PM IST as per business requirements