Job Description
ABOUT THE JOB Architect agentic systems, including planning, memory, tool integration, multi-agent delegation, evaluation loops, and guardrails. Drive model capability into production by designing prompt and context strategies, tool interfaces, retrieval and reranking methods, structured output, streaming, and evaluation across text and multimodal inputs. Lead evaluation efforts by building offline evaluation sets, online LLM-as-judge loops, and regression harnesses. Optimize system performance through prompt caching, batching, speculative decoding, model routing, token budget management, and meeting latency targets. Contribute to upstream development by reading SDK source code, submitting pull requests to open-source agent frameworks, and providing clear bug reports for vendor orchestration services. Mentor team members through design reviews, code reviews, and technical writing, setting high standards for agent system development. ABOUT YOU Bachelor's Degree in Computer Science, Artificial Intelligence or related field. From 5 years of experience in AI Engineering or similar role, with a focus on backend developement. Experience with machine learning fundamentals, including transformers, attention mechanisms, positional encoding, KV cache, tokenization, and sampling. Experience building production systems with advanced language models (Anthropic, OpenAI, Gemini, open-weight), including handling tool-use stability, structured-output failure modes, long-context degradation, prompt-injection defense, and cost control. Experience developing agent systems with planning, memory, tool orchestration, multi-step execution, and error recovery; multi-agent coordination is a strong advantage. Experience with multimodal models (vision-language, document AI, or audio), including data ingestion and grounded output. Advanced proficiency in Python, including asynchronous programming, typing, testing, packaging, and observability; ability to navigate large codebases and maintain code hygiene. Fluent communication in English. You demonstrate strong analytical, mentoring, and communication skills. WHY AMARIS? Competitive salary and 13th-month salary 14+ annual leaves per year Premium healthcare insurance, starting from your probation period Project reviews and yearly performance appraisals Annual company trip Teambuilding activities: Team lunch/dinner, events, and celebrations, sports clubs (football, basketball, badminton, pickleball) International team with flexible working time Tailor-made career path Technical workshops and training courses Mobility: Opportunities to be on-site abroad in our offices in over 60+ countries
