Senior Consultant | Backend Developer | Mumbai | Engineering | Platform Development & Integration
Deloitte Advisory3 days ago
Mumbai, IndiaMid Level / Senior
Responsibilities
- Lead the design and development of agentic and intelligent systems with ownership of core algorithms, model behavior, decision logic, and execution pipelines.
- Architect custom agent orchestration, memory systems, context management, planning, tool-use logic, stateful workflows, fallback logic, and failure handling.
- Build and fine-tune open-source and self-hosted LLMs or hybrid model approaches based on performance, cost, and security trade-offs.
- Develop custom RAG pipelines, embedding strategies, ranking, reranking, and grounding mechanisms for enterprise knowledge systems.
- Integrate agentic solutions with enterprise applications, APIs, data platforms, and internal ML systems.
- Create reusable libraries, low-level design patterns, and internal frameworks for agent-based systems.
- Optimize model inference, reasoning efficiency, latency, cost, response quality, and production performance.
- Establish in-house responsible AI guardrails, explainability, auditability, governance, security, privacy, and access controls.
- Provide production support, deep debugging, root-cause analysis, observability, and performance tuning at system and model levels.
- Mentor junior consultants on AI concepts, algorithms, and system design, and collaborate with engineering, data science, and business teams.
Requirements
- Bachelor’s degree in Computer Science, Engineering, or a related discipline.
- 4 to 7 years of experience building AI-driven systems with demonstrated ownership of model behavior and algorithms.
- Deep understanding of agentic architectures, multi-agent coordination, autonomous decision-making systems, and custom orchestration.
- Ability to design agent frameworks from scratch or significantly extend existing frameworks rather than relying on out-of-the-box abstractions.
- Strong knowledge of LLM internals, transformer architectures, inference behavior, tokenization, attention, and associated trade-offs.
- Experience with open-source LLMs such as LLaMA-family, Mistral, Mixtral, Falcon, and Qwen, including self-hosted deployments.
- Experience with advanced reasoning strategies, planners, critic-agent loops, tool reasoning, and alternatives to chain-of-thought approaches.
- Experience with LangChain, LangGraph, AutoGen, and CrewAI, with the ability to bypass, customize, or replace them with custom implementations.
- Deep experience with RAG pipelines, embeddings, vector similarity search, hybrid retrieval, reranking models, knowledge grounding, information retrieval, indexing, and retrieval algorithms.
- Strong systems engineering skills with Python and/or Java or Go for AI backends.
- Experience deploying AI workloads on GCP, including self-managed inference, GPUs, containers, and scaling strategies.
- Familiarity with MLOps practices including model versioning, evaluation pipelines, controlled rollouts, and experimentation.
- Deep experience with AI observability, including reasoning-path tracing, latency profiling, quality evaluation, and cost monitoring.
- Strong understanding of AI security, data privacy, access control, and compliance.
- General Insurance domain knowledge in Health, Motor, or Travel is preferred.
- Strong ownership, curiosity, collaboration, communication, reliability, and comfort working with ambiguity are expected.
Tech Stack
Categories
About Deloitte Advisory
Deloitte Advisory provides consulting and managed services that help organizations manage risk, strengthen controls, investigate fraud, meet regulatory requirements, and execute transactions using analytics and industry expertise. Offerings span cybersecurity, M&A due diligence, finance and regulatory transformation, internal audit, and tech-enabled platforms. It is part of Deloitte’s global network (founded in 1845 and privately held), with U.S. member-firm teams serving corporations and government agencies across sectors.