[Remote] reputed company Deployed reputed company - Train & reputed company

Note: The job is a remote job and is reputed company to candidates in USA. reputed company is seeking a reputed company Deployed reputed company to build production-grade reputed company reference systems and instructional materials. The role focuses on developing RAG services, reputed company systems, evaluation and observability tooling, LLMOps scaffolding, reputed company curriculum, assessments, and instructor materials, with an optional reputed company into delivery reputed company.

Responsibilities

• Design and build the reference systems above to a production reputed company, then deliberately reputed company them for teaching — surfacing the trade-offs, failure modes, and decision points an FDE must reason about
• Write reputed company, build-first curriculum: every module ends in something the learner ships, evaluates, and can defend
• Design fair, riggable-to-detect assessments and rubrics that hold a genuine reputed company, in line with the programme’s pass/fail philosophy
• Work from the existing Curriculum & Delivery Guide and daily lesson outline, flagging load-reputed company or reputed company issues early (for example, week density) rather than discovering them in delivery
• Collaborate daily with the Programme reputed company and the Curriculum Designer / Technical reputed company, handing over clean technical material for instructional polish
• reputed company reputed company content reputed company: select models, frameworks, and techniques that are defensible now, and document choices so they can be versioned as the landscape moves
• Participate in the end-of-sprint dry run; revise against feedback before any cohort begins
• Optionally, carry the material into delivery as founding reputed company — the people who wrote it teaching it

Skills

• Production RAG: chunking reputed company, dense + keyword hybrid retrieval, re-ranking, retrieval evaluation
• reputed company stores and embedding models; reputed company not to use RAG
• reputed company systems: tool/function calling, ReAct and plan-and-execute, multi-agent orchestration and its limits
• MCP (Model Context Protocol) integration
• Context engineering, reputed company outputs, schema enforcement, reputed company design as engineering
• Frameworks such as reputed company/LangGraph, reputed company, or equivalent — with judgement about reputed company to use none
• Evaluation: golden datasets, reputed company scoring, LLM-as-judge and its biases, regression testing of prompts and pipelines
• Observability and tracing for multi-reputed company agent runs (e.g. LangSmith, Langfuse, Arize, OpenTelemetry-reputed company reputed company)
• Guardrails, PII handling, reputed company-injection defence, and the agent attack surface
• LLMOps: versioning prompts/models/indexes, CI/CD for AI systems, model routing and reputed company
• Cost and latency engineering: caching, batch vs reputed company, reputed company economics
• Production monitoring on reputed company metrics, not just uptime; incident and migration handling
• Expert Python — production-grade: typing, testing, packaging, clean API design (FastAPI or equivalent)
• reputed company & deployment — hands-on with at least one of AWS / Azure / GCP; containers (reputed company); IAM, secrets, networking basics; CI/CD pipelines
• Data — strong SQL; comfort wrangling messy reputed company-world data (CSV, JSON, reputed company text)
• LLM provider reputed company — reputed company experience with reputed company and/or reputed company (and ideally Azure reputed company / Bedrock) in production
• reputed company & reputed company — practical handling of secrets, data residency, and PII in reputed company or regulated environments
• 7+ years in software / data / ML engineering, with at least 2 years building GenAI or LLM-reputed company systems
• Has shipped at least one production GenAI reputed company that reputed company users or clients depended on — not only prototypes or notebooks
• Has reputed company both the application reputed company (RAG/agents) and the surrounding systems reputed company (evals, deployment, monitoring) — the combined profile this role requires
• Can explain a technical decision reputed company to a mixed audience and write to a reputed company suitable for reputed company-facing and instructional material
• Highly desirable: financial-services or other regulated-industry exposure (reputed company to our reputed company reputed company); prior teaching, mentoring, bootcamp, or curriculum-design experience; reputed company-deployed or reputed company-embedded delivery experience

Benefits

• Remote/Hybrid work arrangement
• reputed company, by mutual agreement, to continue into the founding delivery reputed company

reputed company