Expert Consultant, Coro, AI Engineer

AI Engineer – Coro Team

• Design and develop GenAI applications (e.g., copilots, workflow automation, decision support for commercial teams) using modern LLM stacks.
• Implement agentic workflows with clear value—tool use, multi‑step execution, human‑in‑the‑loop controls—focusing on reliability, safety and defined failure modes.
• Build advanced search, retrieval, and knowledge pipelines across hybrid search, vector stores, graph databases, and traditional data platforms, including indexing, metadata design, relevance tuning, freshness, caching, access controls and source attribution.
• Develop robust agent capabilities: context engineering, memory (short‑ and long‑term), orchestration, routing and tool integration patterns.
• Integrate solutions into enterprise environments and workflows (APIs, data systems, collaboration tools) balancing quality, latency, cost, privacy and adoption.
• Translate ambiguous client needs into clear technical requirements, trade‑offs and delivery plans.

• Build ML solutions end‑to‑end: data preparation, feature engineering, model selection, training, validation, testing and performance analysis.
• Apply the right methods—classical ML and deep learning, including transformers and LLM pre‑training/fine tuning—based on the problem scope.
• Create reproducible training and evaluation pipelines with versioning, experiment tracking and clear documentation.
• Demonstrate fluency with modern deep learning concepts, transformer fundamentals and LLM fine‑tuning techniques.

• Write clean, testable, maintainable code and ship AI services through the full SDLC: build, test, deploy, monitor, iterate.
• Implement MLOps and GenAIOps practices (CI/CD, reproducibility, environment parity, model/prompt/agent versioning, operational readiness).
• Build evaluation and observability for GenAI and agentic systems: tracing, instrumentation, regression test suites, automated scoring and iteration loops for prompt and policy optimization.
• Design for secure enterprise deployment: access controls, auditability, data handling for sensitive and PII data, responsible AI guardrails.
• Build reusable components and accelerators (templates, evaluation harnesses, connectors, orchestration patterns) that scale across client contexts.

• Communicate clearly with technical and non‑technical stakeholders; lead working sessions, present recommendations, write concise technical documentation.
• Collaborate with Bain consultants to prioritize technical decisions that unlock business value.
• Support proposal shaping and scoping: effort sizing, architecture options, risk assessment, delivery roadmaps.

• Bachelor’s degree in Computer Science, Engineering or related field, or equivalent practical experience.
• 3–5+ years of professional AI/ML engineering experience, with strong backend engineering fundamentals.
• Strong proficiency in Python; experience building APIs/services (REST/gRPC) and integrating with enterprise systems.
• Hands‑on experience building LLM‑powered applications, considering latency, cost, reliability and security.
• Experience building advanced retrieval/search systems (hybrid retrieval, vector search, reranking) and working across multiple data stores.
• Experience implementing agentic patterns (context management, tool integration, orchestration, memory) using modern frameworks or custom loops, and sound judgment on agentic applicability.
• Experience creating reusable skills, tools and services with schema validation (e.g., Pydantic) for reliable data contracts.
• Proven engineering practices: testing, code review, version control, CI/CD, performance profiling.

• Deploying and operating services on AWS, GCP and/or Azure (environment management, reliability, observability, scaling).
• Docker, Kubernetes or equivalent orchestration; debugging, performance tuning and resilience in production.
• Implement security, privacy, governance for AI systems (authentication/authorization, access controls, PII handling, enterprise risk controls).