AI/ML Engineer: RAG & API Pipelines

Job Description

We're looking for a Senior AI/ML Engineer to act as the bridge between data infrastructure and customer-facing AI products. You'll specialize in building low-latency API layers, production-grade RAG systems, complex ingestion pipelines, and Human-in-the-Loop workflows — working alongside Data Engineers to turn raw data lakes into live AI features.

Requirements

Must-Have Requirements

• Overall Experience: 7+ years in Backend Software Engineering and AI Application Engineering, including exposure to Distributed Systems
• AI & RAG Integration: 2+ years engineering production-grade RAG pipelines, managing vector retrieval context, and implementing secure validation layers for LLMs
• Prototyping & Collaboration: proven track record working synchronously with Data Engineers to rapidly turn raw data lakes and streams into production-ready AI feature prototypes
• Proficiency in Advanced API Design & GraphQL Architecture
• Proficiency in RAG, Data Flows & Ingestion Pipelines
• Proficiency in State Management & Human-in-the-Loop (HITL) Automation
• Production fluency in Python
• Working knowledge of C# (.NET Core), Java, or Node.js/TypeScript for enterprise ingestion systems

Preferred Experience

• Token-aware pagination for GraphQL/REST endpoints (LLM context-safe)
• Custom Model Context Protocol (MCP) server development
• GraphQL schema implementation using Apollo Server or AWS AppSync
• Amazon Bedrock APIs (foundational model invocation and chaining)
• Knowledge Bases for Amazon Bedrock (chunking, metadata extraction, vector sync from S3)
• Hybrid retrieval using OpenSearch/Elasticsearch, pgvector, and MemoryDB / Redis OSS
• High-throughput ingestion workers for embedding and vector generation
• Ingestion pipelines with Amazon SQS, MSK (Kafka), and log sources
• Third-party SaaS analytics API integration (e.g., Pendo, Hotjar, Google Analytics)
• Autonomous Bedrock Agents with action groups
• Amazon Bedrock Guardrails (prompt injection blocking, PII redaction, safety alignment)
• Stateful orchestration with AWS Step Functions or LangGraph
• Durable HITL gating workflows (pause, persist state, resume on human approval)
• Idempotent processing with automated state rollbacks and dead-letter queues (DLQ)
• End-to-end event tracing with OpenTelemetry (oTel) and Datadog

Benefits

• Remote work.
• 13 floating holiday.
• 15 vacation days per year completed.
• Good working environment.

Every qualified candidate who meets the requirements outlined in the job description will be considered in this hiring process without distinction.

Furthermore, Jalasoft is an equal opportunity employer. We wholeheartedly embrace our responsibility to make employment decisions without regard to race, age, marital or social status, national origin, disability, sex, gender identity or expression, or any other characteristic or group of candidates or employees unrelated to their qualifications and suitability for the position. Our management is committed to upholding this policy with respect.