Senior Lead Software Engineer- Python AI

Job Responsibilities: Enhance multiple products across the product line by identifying, prioritizing, and deliveringAI-driven featuresthat improve user experience, efficiency, and operational resilienceDesign, build, and deployproduction-grade AI applicationsincluding LLM-powered workflows, Retrieval-Augmented Generation (RAG) solutions, and agentic systemsBuildagentic workflowswith enterprise-ready controls (identity, authorization, guardrails, tracing, evaluation, and auditability) Developautomation solutionsthat reduce manual effort and eliminate recurring operational issues, including self-healing patterns and intelligent triageArchitect AI systems with production concerns in mind:latency, scalability, cost management, model selection, observability, reliability, and failure modes(including hallucinations and tool errors) Establish and applyAI engineering standardsacross the product line (prompting patterns, RAG design standards, evaluation practices, logging/telemetry, and release readiness criteria) DriveAI architecture reviewsand contribute to reference architectures for model hosting, orchestration, data access, and secure tool executionIdentify and mitigate risks across the AI lifecycle includingdata privacy, security, bias, model misuse, prompt injection, and third-party/vendor risk, and ensure appropriate documentation and controlsPartner with product, design, risk, legal/compliance, and engineering stakeholders to align on outcomes, constraints, and measurable success metricsLead technical evaluations withvendors and platform providers ; assess capabilities, integration fit, security posture, and total cost of ownershipResearch emerging AI capabilities (models, frameworks, tools) and translate findings intopractical guidance, prototypes, and adoption recommendationsEducate and enable teams through documentation, workshops, design reviews, and coaching to raise AI fluency and delivery consistency across the organizationExecute creative software solutions, technical troubleshooting, and hands-on development; write secure, high-quality production code and review/debug code written by othersInfluence stakeholders and drive alignment across teams without direct authority, owning outcomes end-to-endRequired Qualifications, Capabilities, and SkillsFormal training or certification in software engineering concepts and 5+ years of applied engineering experienceHands-on experience delivering AI-powered featuresin production or near-production environments (LLMs, RAG, agents, workflow automation, or decision support systems) Strong proficiency inPython(and ability to build maintainable services, libraries, and pipelines) Experience building APIs and services usingDjango, FastAPI, or similar frameworksExperience building modern UIs usingReactor similar frameworks (or strong ability to partner closely with frontend teams) Strong system design skills with an emphasis onsecure distributed systems, reliability, and operational excellencePractical understanding ofResponsible AI / model risk concepts(evaluation, guardrails, privacy, bias, explainability where applicable, and safe deployment practices) Experience implementingobservability(logging, metrics, tracing) and AI-specific monitoring (quality, drift signals, latency, cost, error rates) Experience withcloud platforms(AWS preferred) and containerized deploymentsStrong problem-solving skills with a structured, evidence-based approach; comfortable operating in ambiguity and delivering iterativelyPreferred Qualifications, Capabilities, and SkillsExperience with AI orchestration and agent frameworks (e.g., LangChain, LlamaIndex, Semantic Kernel, CrewAI, or similar) Experience with vector search and retrieval patterns includingpgvector, Pinecone, Weaviate, OpenSearch/Elastic, or similarExperience designing and operatingRAG systems(chunking strategies, retrieval evaluation, citation/attribution patterns, caching, fallback behaviors) Familiarity withAI governance and standards(model documentation, risk assessments, control frameworks, secure-by-design patterns) and applying them to real delivery timelinesStrong Infrastructure-as-Code experience (e.g., Terraform ) and CI/CD practice, data engineering ecosystems (e.g., Databricks, streaming, data quality controls, lineage concepts)