Job Description:

1. Role Highlights:

Participate in building AI workflow orchestration and automation platforms from scratch (0→1/1→N), covering RAG, tool invocation, Agent collaboration, and asynchronous orchestration.
Implement Diffy or similar "shadow traffic replay + response diff comparison" solutions for model/version regression testing and phased rollouts.
Collaborate with multiple business lines (IM, customer service, marketing automation, data processing, etc.) to deliver real-world, production-grade closed-loop solutions.

Key Responsibilities:

2.1 AI/LLM Workflow Orchestration:

Design and implement multi-step reasoning, Agent collaboration, tool invocation (Tool-Calling/Function-Calling), asynchronous task queues, and compensation mechanisms.
Build and optimize RAG pipelines: data ingestion, chunking, vectorization, retrieval/reranking, context compression, caching, and cost reduction.

2.2 Evaluation & Quality Assurance:

Establish automated evaluation and alignment systems (benchmark sets, Ragas/G-Eval/custom metrics), integrating A/B testing and real-time monitoring.
Leverage Diffy (or equivalent) for shadow traffic replay and response diff analysis to identify regression risks in models/prompts/service upgrades; support canary releases and rollbacks.

2.3 Engineering & Observability:

Develop version control for models/prompts, feature/data versioning, experiment tracking (MLflow/W&B), and audit logs.
Implement end-to-end observability: latency, error rates, prompt/context length, hit rates, and cost monitoring (tokens/$).

2.4 Platform & Integration:

Expose workflows via API/SDK/microservices; integrate with business backends (Go/PHP/Node), queues (Kafka/RabbitMQ), storage (Postgres/Redis/object storage), and vector DBs (Milvus/Qdrant/pgvector).
Ensure security/compliance: anonymization, PII protection, auditing, rate limits, quotas, and model governance.

Job Requirements:

3. Core Requirements:

3+ years in backend/data/platform engineering with 1–2 years of hands-on LLM/generative AI experience.
Proficiency in LLM application engineering: prompt engineering, function/tool calling, dialogue state management, memory, structured output, alignment, and evaluation.
Familiarity with at least one orchestration framework: LangChain/LangGraph, LlamaIndex, Temporal/Prefect/Airflow, or custom DAG/state machine/compensation solutions.
End-to-end RAG experience: data cleaning → vectorization → retrieval → reranking → evaluation; knowledge of Milvus/Qdrant/pgvector.
Experience with Diffy or equivalent traffic replay/diff tools (shadow traffic, record/replay, regression testing, canary deployments).
Strong engineering skills: Docker, CI/CD, Git, logging/metrics (OpenTelemetry/Prometheus/Grafana).
Proficiency in Go/Python/TypeScript; ability to write reliable services and tests.
Remote collaboration and documentation skills; metrics-driven delivery.

4. Preferred Qualifications:

Deep Diffy experience (or shadow traffic/routing via API gateways).
LLMOps/evaluation platform experience (Arize Phoenix, Evidently, PromptLayer, OpenAI Evals, Ragas).
Agent framework implementation (LangGraph, autogen/crewAI, GraphRAG, tool ecosystems).
Security/compliance knowledge (anonymization, PDPA/GDPR, moderation/Llama Guard).
Domain expertise in IM/customer service/marketing automation or multilingual scenarios (Chinese/English/Vietnamese).
Cost optimization: caching, retrieval compression, model routing/multi-provider switching (OpenAI/Anthropic/Google/local models).

5. Tech Stack (Optional):

Orchestration: LangChain/LangGraph, LlamaIndex, Temporal/Prefect/Airflow
Models & Evaluation: OpenAI/Anthropic/Google, VLLM/Ollama, Ragas, G-Eval, MLflow/W&B
Retrieval: Milvus, Qdrant, pgvector, Elasticsearch, rerankers (bge/multilingual/E5)
Services: Go/Python/TypeScript, gRPC/REST, Redis, Postgres, Kafka/RabbitMQ, Docker/K8s
Observability: OpenTelemetry, Prometheus, Grafana, ELK/ClickHouse
Diff/Replay: Twitter Diffy or equivalent shadow traffic/replay systems

Benefits:

Competitive salary, career growth opportunities, collaborative team culture, fully remote work.
Open to university interns with relevant partial experience and guaranteed availability.
Contact: Telegram @Oran_Gina or email [email protected].

🤖

AI Job Analysis

Intelligent Job Recommendations Based on Deep Learning

Ready for Analysis

Analyze Job Core Requirements

This Algorithm Engineer role at Deepcoin requires a unique blend of AI orchestration expertise and production-grade engineering skills. The position focuses on building end-to-end AI workflow systems with strong emphasis on reliability, evaluation, and real-world business integration.

3+ years backend/data/platform engineering with 1–2 years hands-on LLM/generative AI experience
Expertise in LLM orchestration (RAG, tool calling, Agent collaboration) and evaluation systems
Proficiency in implementing Diffy or similar traffic replay systems for model regression testing
Strong engineering fundamentals (Docker, CI/CD, observability) and coding skills (Go/Python/TypeScript)
Experience with AI workflow frameworks like LangChain/LangGraph and vector databases

Understand Employer Recruitment Intent

Deepcoin is likely a tech-forward organization in the cryptocurrency/blockchain space seeking to implement cutting-edge AI solutions across multiple business functions. The detailed technical requirements suggest they're building sophisticated internal AI platforms rather than just implementing off-the-shelf solutions. Their emphasis on shadow traffic testing (Diffy) and canary deployments indicates a strong focus on production reliability - critical in financial/transactional systems. The mention of multilingual support (Chinese/English/Vietnamese) hints at global operations typical in crypto businesses. They appear to be investing heavily in AI infrastructure that can support customer service, marketing automation, and data processing at scale.

MyJob Interviewer Says

As an interviewer for this role, I would prioritize candidates who demonstrate practical experience in shipping production-grade AI systems rather than just theoretical knowledge. The ideal candidate should show: 1) Hands-on examples of implementing RAG pipelines or Agent workflows that solved real business problems, 2) Experience with both the technical implementation and operational aspects (monitoring, evaluation) of AI systems, and 3) The ability to discuss trade-offs in system design decisions. Given the remote nature, clear communication and documentation skills will be equally important as technical capabilities.

AI Matching Suggestions

To stand out for this position at Deepcoin, tailor your application to highlight both technical depth and business impact:

Emphasize production experience with LLM orchestration frameworks (LangChain, LlamaIndex) and measurable outcomes
Showcase specific examples of implementing evaluation systems (Ragas, G-Eval) or traffic replay tools (Diffy)
Highlight any experience in regulated industries or with security/compliance requirements relevant to crypto
Prepare to discuss cost optimization strategies for AI systems (caching, model routing) given their likely need for efficient operations
Demonstrate your ability to work across multiple business domains (IM, customer service, marketing) as required by the role

Algorithm Engineer at Deepcoin

Employment Information

Job Description:

Key Responsibilities:

Job Requirements:

Benefits:

AI Job Analysis

Analyze Job Core Requirements

Understand Employer Recruitment Intent

MyJob Interviewer Says

AI Matching Suggestions

Golang Engineer

$3,000 - $5,500 /hour

Golang Engineer

$3,000 - $5,500 /hour

Business Development

$2,000 - $3,000 /hour

Product Manager

$3,500 - $5,500 /hour

Algorithm Engineer

$2,000 - $5,500 /hour

Language & Currency

Language

Currency

Algorithm Engineer at Deepcoin

Employment Information

Job Description:

Key Responsibilities:

Job Requirements:

Benefits:

$3,000 - $5,500 /hour

$3,000 - $5,500 /hour

$2,000 - $3,000 /hour

$3,500 - $5,500 /hour

$2,000 - $5,500 /hour

New Things Will Always Update Regularly

New Things Will Always
Update Regularly