Artificial Intelligence Engineer

ppOwns end-to-end delivery of how the organization builds LLM-powered applications: SDK/integration architecture, retrieval and agent design, guardrails, and evaluation. Makes the calls on which LLMs to use for which use cases and sets the observability/cost discipline around AI systems, but is measured on shipped outcomes — runs the offshore team day-to-day and stays hands‑on to unblock delivery risk. /p h3Key Responsibilities /h3 ul liOwn delivery of LLM API integration and SDK patterns used across applications. /li liSet organizational guidance on which LLM to use for what use case and drive delivery of multi-LLM scenarios. /li liDefine standards for advanced prompt engineering and context window management. /li liOwn delivery of RAG systems, including vector database selection/topology and knowledgebase design. /li liDrive delivery of AI agent and multi-agent systems and tool-use/MCP integration patterns. /li liOwn guardrails delivery (safety, compliance, PII handling in prompts/outputs) — critical in a financial-services context. /li liDefine evaluation frameworks and real-time eval strategy; set standards for AI testing in CI/CD. /li liOwn latency profiling, AI observability, and cost tracking/management for LLM-backed systems. /li liRun day-to-day delivery of the offshore development team: sprint commitments, code/design review, real-time unblocking, and hands‑on work on critical-path AI features. /li liReport delivery status, risks, and blockers to engineering leadership. /li /ul h3Must-Have Qualifications /h3 ul li6+ years in software engineering, with 2+ years as a tech lead owning end-to-end delivery of LLM/AI-powered systems (not a pure design/review architect role). /li liProven track record of shipping AI-powered features on committed timelines, including hands‑on troubleshooting under delivery pressure. /li liStrong, hands‑on Python skills at an architectural/systems level. /li liProven experience architecting LLM API integrations and SDK-level abstractions across multiple providers. /li liDemonstrated judgment on model selection (cost, latency, capability trade-offs) across use cases. /li liDeep expertise in prompt engineering and context window management at scale. /li liProven design experience with RAG systems, including vector database architecture and knowledgebase design. /li liExperience architecting AI agents/multi-agent systems and tool-use patterns (MCP or equivalent). /li liStrong understanding of guardrails design — content safety, PII protection, compliance controls for AI outputs. /li liExperience defining evaluation frameworks and integrating AI testing into CI/CD. /li liProven ability to design for latency, observability, and cost management of AI systems in production. /li liFinancial-services or regulated-industry experience strongly preferred given compliance/guardrail stakes. /li liStrong stakeholder communication; able to directly manage day-to-day delivery of an offshore team (standups, unblocking, sprint accountability). /li liMinimum Educational Qualification
- Bachelors Degree /li /ul h3Nice-to-Have Qualifications /h3 ul liDirect experience with specific frameworks (LangChain, LlamaIndex, Semantic Kernel, or equivalent). /li liExperience with AWS Bedrock or comparable managed LLM platforms. /li liContributions to or deep familiarity with MCP (Model Context Protocol) implementations. /li liExperience building internal LLM gateways. /li liFamiliarity with responsible‑AI/model-risk-management frameworks used in financial services. /li /ul /p