Principal AI Engineer - Java

Title: Principal AI EngineerLocation: US(NYC)- 3(WFO)About The Role8–14 years of software engineering experience, with strong hands-on large-scale PythonWorking depth in at least one systems or backend language — Go, Rust, Java, or C/C++ — and the judgment to know when to reach for itStrong data structures and algorithms.Strong understanding of APIs, microservices, and system designHands-on experience building and operating data pipelines and production-grade distributed systems.Agentic AI and LLMs2+ years of hands-on LLM engineering, with at least couple agentic system you designed and took to productionProduction experience with agent frameworks — LangGraph, Google ADK, CrewAI, Claude Agent SDK, or equivalent — and the fluency to move between them as the ecosystem evolvesExperience building MCP (Model Context Protocol) servers and tool-calling interfacesRAG from first principles: chunking strategy, embeddings, vector and hybrid retrieval, reranking, and response validationStrong experience with vector databases (Milvus, Pinecone, Weaviate, FAISS, etc. or cloud equivalents)Design of guardrails and reliability patterns — validators, policy checks, self-correction loops, deterministic fallbacks, circuit breakers, and rollback pathsOptimizationDeep familiarity with token optimization and context-window management — context shaping, pruning, and compactionLatency and cost optimization through caching, model routing, batching, streaming, and parallel tool callsPerformance testing and tuning systems against defined SLOsEvaluationExperience building evaluation frameworks for LLM systems — offline eval sets, continuous online evaluation, and regression detectionInstrumentation and traceability suitable for regulated enterprise environments using tools like LangSmith, Langfuse, etc.CloudHands-on AWS: containerized services (ECS/EKS), serverless (Lambda), data services (S3, DynamoDB, Redshift) and orchestration (Step Functions); Azure or GCP equivalents also valuedFamiliarity with CI/CD pipelines and DevOps practicesInfrastructure as code with Terraform or CloudFormation, and mature CI/CD practiceWorking traitsStrong analytical problem-solving with a bias to ownership and urgencyClear cross-team communication, working directly with client stakeholders to translate business problems into technical roadmapsAble to work productively in ambiguity from system-level documentation and ramp quickly in unfamiliar codebasesGood to HaveExperience with managed AI platforms — Amazon Bedrock, Vertex AI, Azure AI — paired with fluency in the underlying fundamentalsRoles & ResponsibilitiesDesign and build agentic systems: Lead the architecture and implementation of tool-calling agents that combine retrieval, structured reasoning, and secure action execution with least-privilege access.Productionize LLM applications: Build retrieval pipelines, prompt synthesis, response validation, and self-correction loops, backed by rigorous evaluation.Own the full stack: Deliver the data pipelines, backend services, distributed compute, and orchestration layer that agentic systems depend on — not only the model invocation.Engineer for reliability and governance: Build validator models, adversarial test suites, and policy checks; enforce deterministic fallbacks and rollback strategies; instrument continuous evaluation.Optimize for cost and latency: Drive measurable improvements in token efficiency, response time, and unit economics against defined SLOs.Codebase ownership: Build, maintain, and review high-quality Python and SQL, with an emphasis on reusable components, scalability, and performance.Cloud integration: Deploy AI applications on AWS, Azure, or GCP with optimized resource usage and robust CI/CD.Cross-functional collaboration: Partner with product owners, data scientists, and business SMEs to define requirements and deliver impactful AI products.Mentoring and technical leadership: Set engineering standards and share knowledge across the team, raising the bar on AI and software engineering practice.About ApTask:ApTask is a leading global provider of workforce solutions and talent acquisition services, dedicated to shaping the future of work. As an African American-owned and Veteran-owned company, ApTask offers a comprehensive suite of services, including staffing and recruitment solutions, managed services, IT consulting, and project management. With a focus on excellence, collaboration, and innovation, ApTask provides unparalleled opportunities for professional growth and development. As a member of the ApTask team, you will have the chance to connect businesses with top-tier professionals, optimize workforce performance, and drive success across diverse industries. Join us at ApTask and be part of our mission to empower organizations to thrive while fostering a diverse and inclusive work environment.Applicants may be required to attend interviews in person or by video conference. In addition, candidates may be required to present their current state or government issued ID during each interview.Candidate Data Collection Disclaimer:At ApTask, we prioritize safeguarding your privacy. As part of our recruitment process, certain Personally Identifiable Information (PII) may be requested by our clients for verification and application purposes. Rest assured, we strictly adhere to confidentiality standards and comply with all relevant data protection laws. Please note that we only collect the necessary information as specified by each client and do not request sensitive details during the initial stages of recruitment.If you have any concerns or queries about your personal information, please feel free to contact our compliance team at compliance@aptask.com.Applicant Consent:By submitting your application, you agree to ApTask's (www.aptask.com) Terms of Use and Privacy Policy, and provide your consent to receive SMS and voice call communications regarding employment opportunities that match your resume and qualifications. You understand that your personal information will be used solely for recruitment purposes and that you can withdraw your consent at any time by contacting us at 732-355-8000 or help@aptask.com. Message frequency may vary. Msg & data rates may apply.