AI Tech Lead

Cross-Team Technical Coordination Serving as Scrum Master and Delivery Lead for both AI teams: organizing and facilitating sprint planning, daily stand-ups, backlog grooming, and retrospectives. Shielding both teams from day-to-day integration distractions by ensuring the junior development team receives clean task definitions, structured schemas, and clearly scoped technical requirements. Balancing high-speed AI prototyping demands against the structured pipeline stabilization cycles required for enterprise-grade development. Managing cross-team dependency and interface mapping to ensure smooth collaboration between the senior and junior engineering layers. Architecture Translation & Gateway Translating strict architectural guardrails — network isolation, database connection limits, cost-containment — from the System Architects into practical workflows for the engineering teams. Partnering with Loftware Architects to ensure teams safely leverage AWS services and data read replicas without compromising corporate security boundaries, tenant isolation, or regional compliance. Leading technical review sessions to determine the appropriate storage strategy (Amazon MemoryDB / Redis OSS / Valkey vs. pgvector vs. OpenSearch), balancing developer needs against enterprise infrastructure standards. AI & LLM Systems Quality Control Overseeing evaluation frameworks for multi-step agent workflows to ensure deterministic behavior and eliminate unhandled hallucinations. Validating that all data ingestion flows and internal tool-calling structures adhere to type-safe validation layers, preventing malformed agent responses from breaking downstream systems or leaking PII. Overseeing the centralized repository for system prompts, prompt caching strategies, and Amazon Bedrock configurations to ensure optimal performance, token budgeting, and corporate policy alignment. Enterprise Deployment & Operational Stability Working with internal teams to define and enforce robust CI/CD strategies for AI agents, ensuring that changes to prompts, embeddings, or state-machine routing rules are deployed without service disruption. Contributing to operational protocols for deployment failures mid-workflow, ensuring both teams design for idempotency to handle unexpected model degradation or pipeline failures gracefully. 10+ years of experience in Software Engineering and/or Technical Leadership 3+ years leading AI/ML or high-throughput distributed systems teams Proven track record running agile methodologies (Scrum/Kanban) across multi-tiered or split engineering teams Deep hands-on architectural experience with LLMs and enterprise-scale systems Experience partnering with System Architects to govern AWS infrastructure usage, security controls, and resource provisioning Familiarity with agentic orchestration frameworks (LangGraph, AWS Step Functions, or equivalent) at an architectural governance level Working knowledge of Amazon Bedrock APIs, Guardrails, and Knowledge Base configurations Understanding of vector retrieval strategies (pgvector, Amazon OpenSearch/Elasticsearch) and in-memory data stores (Amazon MemoryDB / Redis OSS / Valkey) Experience designing for idempotency and stateful rollback in distributed AI pipelines Strong stakeholder management skills, with experience negotiating architectural and infrastructure decisions on behalf of engineering teams Hands-on implementation experience with Vercel AI SDK, LangGraph, or LlamaIndex 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.