Forward Deployed AI Engineer (Java experience)

We're looking for a Forward Deployed AI Engineer who combines strong software engineering fundamentals with hands-on AI/LLM engineering and a customer-first mindset. You'll embed with customers and internal partner teams to design, build, and ship production-grade, AI-powered solutions - from intelligent integrations to LLM-driven agents and services - translating real-world business problems into robust, scalable systems. 

This is a role for engineers who love writing strong Java code, building with modern AI, and working shoulder-to-shoulder with the people using what they build. You won't be handed a spec and left alone: you'll uncover requirements, make architectural calls, wire up AI capabilities that actually work in production, and own the outcome end to end. 

Location: Remote in LATAM. Working hours are based on the US Central or Eastern Time Zone.

About the Company:

Abstra is a fast-growing, Nearshore Tech Talent services company, providing top Latin American tech talent to U.S. companies and beyond. Founded by U.S.-bred engineers with over 15 years of experience, Abstra specializes in sourcing skilled professionals across a wide range of technologies to meet our clients’ needs, driving innovation and efficiency.

What You'll Do 

• Build production services in Java — design and implement microservices (Spring Boot) that integrate customer systems with our platform and AI capabilities. 

• Engineer AI-powered features — build LLM/GenAI applications using model APIs (Anthropic Claude, OpenAI, AWS Bedrock, etc.): RAG pipelines, agentic workflows, tool/function calling, prompt engineering, and evaluation. 

• Deploy and operate on the cloud — build, ship, and run services and AI workloads on AWS, containerized and orchestrated with Kubernetes. 

• Embed with customers/partners — work directly with client teams to gather requirements, design AI solutions, and drive them to go-live — including responsibly setting expectations about what AI can and can't do. 

• Own the full lifecycle — discovery, design, implementation, evaluation, deployment, and post-launch support of both services and AI features. 

• Make AI production-ready — handle the hard parts: grounding/hallucination control, latency and cost optimization, guardrails, observability, and evaluation/testing of non-deterministic systems. 

• Debug across the stack — diagnose issues spanning distributed systems, APIs, data pipelines, model integrations, and infrastructure. 

• Translate ambiguity into architecture — turn loosely-defined business needs into clear technical designs; push back when there's a better or safer approach. 

• Improve the platform — feed field learnings back into the product; build reusable AI patterns, tooling, prompts, and documentation. 

What You'll Need (Required) 

• 3+ years of professional software engineering experience with strong Java (Java 8–21). 

• Hands-on experience with Spring Boot and building/consuming RESTful APIs. 

• Applied AI/LLM engineering experience — you've built and shipped something real with LLMs: e.g. RAG, agents, tool calling, prompt engineering, or model-API integration (Claude, OpenAI, Bedrock, Gemini, or similar). 

• Exposure to AWS — deploying and running applications using core services (EC2, S3, IAM, RDS, Lambda, CloudWatch); familiarity with AWS AI/ML services (e.g. Bedrock, SageMaker) a strong plus. 

• Exposure to Kubernetes — deploying, running, and troubleshooting containerized workloads (Docker + K8s). 

• Solid grasp of relational databases (SQL); familiarity with vector databases / embeddings for retrieval. 

• Strong debugging and problem-solving skills across distributed and AI-integrated systems. 

• Excellent communication — comfortable working directly with customers and non-technical stakeholders, including explaining AI capabilities and limitations. 
• Bachelor's degree in Computer Science or equivalent practical experience. 
• Experience with Kotlin or Python (common for AI/ML tooling); JVM build tools (Maven / Gradle). 

• Agentic frameworks / orchestration — LangChain, LlamaIndex, Spring AI, Model Context Protocol (MCP), or similar. 

• LLM evaluation & observability — building eval harnesses, prompt/version management, tracing (LangSmith, Langfuse, or homegrown). 

• Classic ML / MLOps — model training, fine-tuning, feature stores, model serving, and deployment pipelines. 

• CI/CD and infrastructure-as-code (Terraform, Helm, CloudFormation). 

• Event-driven / streaming systems (Kafka, SQS/SNS) and microservices patterns. 

• Awareness of responsible AI — safety, guardrails, PII handling, prompt-injection defense, and data privacy. 

• Prior customer-facing / consulting / implementation engineering experience. 

What We Offer:

• Competitive compensation paid in USD.
• 20 days of paid time off (PTO) per year.
• Opportunities for professional growth and career development.
• Company-provided equipment.
• A collaborative, inclusive, and multicultural work environment.
• The opportunity to contribute to meaningful projects alongside a talented and supportive team.
  

Pre-Employment Verification
As part of our standard onboarding process, candidates who successfully complete the interview process and accept an employment offer will be required to complete an employment verification check, and background check. This process will confirm job titles and dates of employment with two previous employers and is a standard requirement for all new employees joining the company.